baari 0.1.0__tar.gz

baari-0.1.0/.gitignore

@@ -0,0 +1,8 @@
+.env
+.venv/
+.uv-cache/
+data/
+__pycache__/
+*.egg-info/
+dist/
+.uv-python/

baari-0.1.0/LICENSE

@@ -0,0 +1,24 @@
+BSD 2-Clause License
+
+Copyright (c) 2026, Abdul Samad
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

baari-0.1.0/LICENSE.indic-smart-turn

@@ -0,0 +1,27 @@
+Parts of src/baari/clips.py and prompts/label.md are adapted from Indic Smart Turn
+(https://github.com/adimyth/indic-smart-turn), under this license:
+
+BSD 2-Clause License
+
+Copyright (c) 2026, adimyth
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

baari-0.1.0/LICENSE.pipecat

@@ -0,0 +1,24 @@
+BSD 2-Clause License
+
+Copyright (c) 2024–2025, Daily
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

baari-0.1.0/PKG-INFO

@@ -0,0 +1,166 @@
+Metadata-Version: 2.5
+Name: baari
+Version: 0.1.0
+Summary: End-of-turn detection for Urdu voice agents
+Project-URL: Homepage, https://github.com/samadpls/baari
+Project-URL: Issues, https://github.com/samadpls/baari/issues
+Project-URL: Author, https://samadpls.com
+Author-email: Abdul Samad <abdulsamadsid1@gmail.com>
+License-Expression: BSD-2-Clause
+License-File: LICENSE
+License-File: LICENSE.indic-smart-turn
+License-File: LICENSE.pipecat
+Keywords: end-of-turn,onnx,pipecat,speech,turn-detection,urdu,voice-agents
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Natural Language :: Urdu
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Requires-Dist: numpy
+Requires-Dist: onnxruntime
+Provides-Extra: pipeline
+Requires-Dist: huggingface-hub>=0.30; extra == 'pipeline'
+Requires-Dist: onnx; extra == 'pipeline'
+Requires-Dist: pyarrow>=17; extra == 'pipeline'
+Requires-Dist: pydantic-settings>=2; extra == 'pipeline'
+Requires-Dist: pydantic>=2; extra == 'pipeline'
+Requires-Dist: scikit-learn; extra == 'pipeline'
+Requires-Dist: soundfile; extra == 'pipeline'
+Requires-Dist: torch; extra == 'pipeline'
+Requires-Dist: transformers>=4.48; extra == 'pipeline'
+Requires-Dist: typer; extra == 'pipeline'
+Description-Content-Type: text/markdown
+
+<p align="center">
+  <img alt="baari: knows when an Urdu speaker has finished talking" src="https://raw.githubusercontent.com/samadpls/baari/main/assets/hero.svg" width="100%">
+</p>
+
+<p align="center">
+  <a href="https://samadpls.com"><img alt="by samadpls.com" src="https://img.shields.io/badge/by-samadpls.com-0E6B4F"></a>
+  <a href="https://github.com/samadpls/baari/blob/main/LICENSE"><img alt="Code license: BSD-2-Clause" src="https://img.shields.io/badge/code-BSD--2--Clause-0E6B4F"></a>
+  <a href="https://huggingface.co/datasets/ai4bharat/IndicVoices"><img alt="Data: IndicVoices, CC BY 4.0" src="https://img.shields.io/badge/data-IndicVoices%20(CC%20BY%204.0)-F2B544?logo=huggingface&logoColor=000"></a>
+  <a href="https://pypi.org/project/baari/"><img alt="PyPI" src="https://img.shields.io/pypi/v/baari?color=0E6B4F&label=pypi"></a>
+  <a href="https://pepy.tech/projects/baari"><img alt="Downloads" src="https://static.pepy.tech/badge/baari"></a>
+  <img alt="Python 3.10+" src="https://img.shields.io/badge/python-3.10%2B-3776AB?logo=python&logoColor=fff">
+</p>
+
+<p align="center">
+  <b>End-of-turn detection for Urdu voice agents.</b><br>
+  At every pause, it decides whether the speaker has finished (reply now) or is only pausing mid-sentence (keep listening).
+</p>
+
+---
+
+baari (باری) means "turn" in Urdu. The table below shows that today's turn detectors often cut Urdu
+speakers off mid-sentence, or wait after they have finished. baari is a small audio model trained to
+get this right. It follows the [Smart Turn](https://github.com/pipecat-ai/smart-turn) recipe and takes
+the same input and output, so it can stand in for Smart Turn.
+
+**Status: work in progress.** Done so far: the Urdu test set, the scores of existing models, and
+labels for 61,251 training segments. The training code is in place. The first model hasn't been
+trained yet.
+
+## 🎧 Do existing models understand Urdu?
+
+1,588 clips of real Urdu phone conversations, cut from the official held-out split of IndicVoices: 1,470
+where the speaker had finished and 118 where they were pausing mid-sentence. Because most clips are
+"finished", a model that always says "finished" gets 92.6% plain accuracy, so the fair score is the
+average of the two middle columns (balanced accuracy).
+
+| Model | Balanced accuracy (95% CI) | Waits when unfinished | Replies when finished |
+|---|---|---|---|
+| Always says "finished" (reference) | 50.0% | 0.0% | 100.0% |
+| Smart Turn v3.2 (CPU, int8) | 63.4% (58.8–68.1) | 57.6% | 69.2% |
+| Smart Turn v3.2 (GPU, fp32) | 58.8% (54.8–63.0) | 76.3% | 41.3% |
+| Indic Smart Turn tiny (int8) | 73.4% (69.0–77.8) | 61.0% | 85.9% |
+| Indic Smart Turn tiny (fp32) | 70.0% (65.8–74.4) | 51.7% | 88.4% |
+| Indic Smart Turn base (fp32) | 70.9% (66.5–75.4) | 47.5% | 94.4% |
+| PuristanLabs1/urdu-turn-v2 (Urdu) | 51.8% (48.4–55.4) | 16.9% | 86.7% |
+
+Scored on a MacBook Pro (M3 Pro), with the same audio preparation Pipecat uses. int8 models are
+sensitive: their scores shift by a few points between Arm and x86 CPUs, and even tiny changes in how
+the audio is prepared flip about 1 answer in 100. fp32 results stay the same.
+
+<details>
+<summary>How the test set was made</summary>
+
+- **Source:** the conversation recordings in the `valid` split of
+  [IndicVoices](https://huggingface.co/datasets/ai4bharat/IndicVoices) Urdu (CC BY 4.0): 1,654 segments,
+  81 calls, 80 speakers, 1.7 hours. Each segment ends at a pause.
+- **Labels:** two LLM agents each read every call's transcript in order and marked whether the speaker
+  had finished at the end of each segment ([prompt](https://github.com/samadpls/baari/blob/main/prompts/label.md)). They agreed on 96.0%. Agreed
+  segments form the test set; the 66 others are kept apart as `test_ambiguous`.
+- **Clips:** the last 8 s of 16 kHz audio ending at the segment, with the speaker's preceding segments
+  as context, the same recipe as [Indic Smart Turn](https://github.com/adimyth/indic-smart-turn).
+- **Checked by ear:** a native speaker listened to 50 random clips. All 25 "finished" labels were
+  right, and 19 of 25 "unfinished" labels were. In the wrong ones the words stop mid-sentence but the
+  voice sounds finished, which a transcript cannot show. So roughly 1 in 4 "unfinished" clips may
+  really be finished, and the "waits when unfinished" column is a rough measure.
+- **Leakage:** 70 of the 80 test speakers, and the other side of 57 of the 81 test calls, also appear in
+  the IndicVoices `train` split. Any training data will leave out those speakers and calls.
+
+</details>
+
+## Use it
+
+```bash
+pip install baari
+```
+
+```python
+from baari import TurnDetector
+
+detector = TurnDetector(threads=4)  # downloads baari's 9 MB int8 model once
+detector.is_finished(audio)  # 16 kHz mono audio (float or int16) that ends at the pause
+detector.probability(audio)  # the same decision as a number from 0 to 1
+```
+
+It needs only numpy and onnxruntime. One call takes about 12 ms on 4 CPU threads and 37 ms on one
+(MacBook Pro, M3 Pro). Use `threads=1` on a server that handles many calls at once.
+
+**The baari model is not released yet.** Until it is, `TurnDetector(path=...)` runs any Smart Turn
+style ONNX file, such as [Indic Smart Turn tiny](https://huggingface.co/adimyth/indic-smart-turn), the
+best existing model in the table above.
+
+## 🛠️ Run it
+
+```bash
+uv sync --extra pipeline
+echo "HF_TOKEN=..." > .env          # accept the IndicVoices terms on Hugging Face first
+uv run baari scan --split valid     # index the conversation segments (text only)
+uv run baari batches                # label batches for the LLM agents
+# the agents write data/labels/valid/results/{a,b}/batch-*.jsonl
+uv run baari build                  # cut the 8 s clips
+uv run baari evaluate               # score the existing models
+```
+
+<details>
+<summary>Training</summary>
+
+The same steps on the IndicVoices `train` split, with one labeler. Test speakers and both sides of
+test calls are left out, and about 5% of the remaining speakers form a dev split that picks the best
+epoch.
+
+```bash
+uv run baari scan --split train
+uv run baari batches --split train
+# the agents write data/labels/train/results/a/batch-*.jsonl
+uv run baari build --split train --labelers a --delete-shards
+uv run baari train                  # fine-tune Indic Smart Turn tiny, export fp32 and int8 ONNX
+```
+
+Training starts from Indic Smart Turn tiny. That model ships only as ONNX, so `baari train` first
+reads its weights back into PyTorch. The [kaggle](https://github.com/samadpls/baari/tree/main/kaggle) folder runs the clip build and the
+training on Kaggle.
+
+</details>
+
+---
+
+<p align="center">
+  <a href="https://github.com/samadpls/baari/blob/main/docs/CREDITS.md">Credits</a> · <a href="https://github.com/samadpls/baari/blob/main/CONTRIBUTING.md">Contributing</a> · <a href="https://github.com/samadpls/baari/blob/main/LICENSE">BSD-2-Clause license</a><br>
+  Made by <a href="https://samadpls.com">Abdul Samad</a> (abdulsamadsid1@gmail.com)
+</p>

baari-0.1.0/README.md

@@ -0,0 +1,130 @@
+<p align="center">
+  <img alt="baari: knows when an Urdu speaker has finished talking" src="https://raw.githubusercontent.com/samadpls/baari/main/assets/hero.svg" width="100%">
+</p>
+
+<p align="center">
+  <a href="https://samadpls.com"><img alt="by samadpls.com" src="https://img.shields.io/badge/by-samadpls.com-0E6B4F"></a>
+  <a href="https://github.com/samadpls/baari/blob/main/LICENSE"><img alt="Code license: BSD-2-Clause" src="https://img.shields.io/badge/code-BSD--2--Clause-0E6B4F"></a>
+  <a href="https://huggingface.co/datasets/ai4bharat/IndicVoices"><img alt="Data: IndicVoices, CC BY 4.0" src="https://img.shields.io/badge/data-IndicVoices%20(CC%20BY%204.0)-F2B544?logo=huggingface&logoColor=000"></a>
+  <a href="https://pypi.org/project/baari/"><img alt="PyPI" src="https://img.shields.io/pypi/v/baari?color=0E6B4F&label=pypi"></a>
+  <a href="https://pepy.tech/projects/baari"><img alt="Downloads" src="https://static.pepy.tech/badge/baari"></a>
+  <img alt="Python 3.10+" src="https://img.shields.io/badge/python-3.10%2B-3776AB?logo=python&logoColor=fff">
+</p>
+
+<p align="center">
+  <b>End-of-turn detection for Urdu voice agents.</b><br>
+  At every pause, it decides whether the speaker has finished (reply now) or is only pausing mid-sentence (keep listening).
+</p>
+
+---
+
+baari (باری) means "turn" in Urdu. The table below shows that today's turn detectors often cut Urdu
+speakers off mid-sentence, or wait after they have finished. baari is a small audio model trained to
+get this right. It follows the [Smart Turn](https://github.com/pipecat-ai/smart-turn) recipe and takes
+the same input and output, so it can stand in for Smart Turn.
+
+**Status: work in progress.** Done so far: the Urdu test set, the scores of existing models, and
+labels for 61,251 training segments. The training code is in place. The first model hasn't been
+trained yet.
+
+## 🎧 Do existing models understand Urdu?
+
+1,588 clips of real Urdu phone conversations, cut from the official held-out split of IndicVoices: 1,470
+where the speaker had finished and 118 where they were pausing mid-sentence. Because most clips are
+"finished", a model that always says "finished" gets 92.6% plain accuracy, so the fair score is the
+average of the two middle columns (balanced accuracy).
+
+| Model | Balanced accuracy (95% CI) | Waits when unfinished | Replies when finished |
+|---|---|---|---|
+| Always says "finished" (reference) | 50.0% | 0.0% | 100.0% |
+| Smart Turn v3.2 (CPU, int8) | 63.4% (58.8–68.1) | 57.6% | 69.2% |
+| Smart Turn v3.2 (GPU, fp32) | 58.8% (54.8–63.0) | 76.3% | 41.3% |
+| Indic Smart Turn tiny (int8) | 73.4% (69.0–77.8) | 61.0% | 85.9% |
+| Indic Smart Turn tiny (fp32) | 70.0% (65.8–74.4) | 51.7% | 88.4% |
+| Indic Smart Turn base (fp32) | 70.9% (66.5–75.4) | 47.5% | 94.4% |
+| PuristanLabs1/urdu-turn-v2 (Urdu) | 51.8% (48.4–55.4) | 16.9% | 86.7% |
+
+Scored on a MacBook Pro (M3 Pro), with the same audio preparation Pipecat uses. int8 models are
+sensitive: their scores shift by a few points between Arm and x86 CPUs, and even tiny changes in how
+the audio is prepared flip about 1 answer in 100. fp32 results stay the same.
+
+<details>
+<summary>How the test set was made</summary>
+
+- **Source:** the conversation recordings in the `valid` split of
+  [IndicVoices](https://huggingface.co/datasets/ai4bharat/IndicVoices) Urdu (CC BY 4.0): 1,654 segments,
+  81 calls, 80 speakers, 1.7 hours. Each segment ends at a pause.
+- **Labels:** two LLM agents each read every call's transcript in order and marked whether the speaker
+  had finished at the end of each segment ([prompt](https://github.com/samadpls/baari/blob/main/prompts/label.md)). They agreed on 96.0%. Agreed
+  segments form the test set; the 66 others are kept apart as `test_ambiguous`.
+- **Clips:** the last 8 s of 16 kHz audio ending at the segment, with the speaker's preceding segments
+  as context, the same recipe as [Indic Smart Turn](https://github.com/adimyth/indic-smart-turn).
+- **Checked by ear:** a native speaker listened to 50 random clips. All 25 "finished" labels were
+  right, and 19 of 25 "unfinished" labels were. In the wrong ones the words stop mid-sentence but the
+  voice sounds finished, which a transcript cannot show. So roughly 1 in 4 "unfinished" clips may
+  really be finished, and the "waits when unfinished" column is a rough measure.
+- **Leakage:** 70 of the 80 test speakers, and the other side of 57 of the 81 test calls, also appear in
+  the IndicVoices `train` split. Any training data will leave out those speakers and calls.
+
+</details>
+
+## Use it
+
+```bash
+pip install baari
+```
+
+```python
+from baari import TurnDetector
+
+detector = TurnDetector(threads=4)  # downloads baari's 9 MB int8 model once
+detector.is_finished(audio)  # 16 kHz mono audio (float or int16) that ends at the pause
+detector.probability(audio)  # the same decision as a number from 0 to 1
+```
+
+It needs only numpy and onnxruntime. One call takes about 12 ms on 4 CPU threads and 37 ms on one
+(MacBook Pro, M3 Pro). Use `threads=1` on a server that handles many calls at once.
+
+**The baari model is not released yet.** Until it is, `TurnDetector(path=...)` runs any Smart Turn
+style ONNX file, such as [Indic Smart Turn tiny](https://huggingface.co/adimyth/indic-smart-turn), the
+best existing model in the table above.
+
+## 🛠️ Run it
+
+```bash
+uv sync --extra pipeline
+echo "HF_TOKEN=..." > .env          # accept the IndicVoices terms on Hugging Face first
+uv run baari scan --split valid     # index the conversation segments (text only)
+uv run baari batches                # label batches for the LLM agents
+# the agents write data/labels/valid/results/{a,b}/batch-*.jsonl
+uv run baari build                  # cut the 8 s clips
+uv run baari evaluate               # score the existing models
+```
+
+<details>
+<summary>Training</summary>
+
+The same steps on the IndicVoices `train` split, with one labeler. Test speakers and both sides of
+test calls are left out, and about 5% of the remaining speakers form a dev split that picks the best
+epoch.
+
+```bash
+uv run baari scan --split train
+uv run baari batches --split train
+# the agents write data/labels/train/results/a/batch-*.jsonl
+uv run baari build --split train --labelers a --delete-shards
+uv run baari train                  # fine-tune Indic Smart Turn tiny, export fp32 and int8 ONNX
+```
+
+Training starts from Indic Smart Turn tiny. That model ships only as ONNX, so `baari train` first
+reads its weights back into PyTorch. The [kaggle](https://github.com/samadpls/baari/tree/main/kaggle) folder runs the clip build and the
+training on Kaggle.
+
+</details>
+
+---
+
+<p align="center">
+  <a href="https://github.com/samadpls/baari/blob/main/docs/CREDITS.md">Credits</a> · <a href="https://github.com/samadpls/baari/blob/main/CONTRIBUTING.md">Contributing</a> · <a href="https://github.com/samadpls/baari/blob/main/LICENSE">BSD-2-Clause license</a><br>
+  Made by <a href="https://samadpls.com">Abdul Samad</a> (abdulsamadsid1@gmail.com)
+</p>

baari-0.1.0/pyproject.toml

@@ -0,0 +1,58 @@
+[project]
+name = "baari"
+version = "0.1.0"
+description = "End-of-turn detection for Urdu voice agents"
+readme = "README.md"
+license = "BSD-2-Clause"
+authors = [{ name = "Abdul Samad", email = "abdulsamadsid1@gmail.com" }]
+requires-python = ">=3.10"
+dependencies = ["numpy", "onnxruntime"]
+keywords = ["urdu", "turn-detection", "end-of-turn", "voice-agents", "speech", "pipecat", "onnx"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Natural Language :: Urdu",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Topic :: Multimedia :: Sound/Audio :: Speech",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+
+[project.urls]
+Homepage = "https://github.com/samadpls/baari"
+Issues = "https://github.com/samadpls/baari/issues"
+Author = "https://samadpls.com"
+
+[project.optional-dependencies]
+pipeline = [
+    "huggingface_hub>=0.30",
+    "pyarrow>=17",
+    "soundfile",
+    "transformers>=4.48",
+    "scikit-learn",
+    "pydantic>=2",
+    "pydantic-settings>=2",
+    "typer",
+    "torch",
+    "onnx",
+]
+
+[project.scripts]
+baari = "baari.cli:app"
+
+[dependency-groups]
+dev = ["pytest", "ruff"]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.sdist]
+# An allow-list, so local-only files (the plan, data, .env) can never end up in a release.
+include = ["src/baari", "tests", "LICENSE*", "README.md", "pyproject.toml"]
+
+[tool.uv]
+cache-dir = ".uv-cache"
+
+[tool.ruff]
+line-length = 110

baari-0.1.0/src/baari/__init__.py

@@ -0,0 +1,5 @@
+"""End-of-turn detection for Urdu voice agents."""
+
+from baari.detector import TurnDetector, model_path
+
+__all__ = ["TurnDetector", "model_path"]